Ruben2003's picture
First Push
1f27cda verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8700188398361206,
"min": 0.8700188398361206,
"max": 2.855184316635132,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8268.6591796875,
"min": 8268.6591796875,
"max": 29145.72265625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.86416244506836,
"min": 0.3632872402667999,
"max": 12.89290714263916,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.51171875,
"min": 70.47772216796875,
"max": 2624.08154296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06386416716807564,
"min": 0.061661368265277794,
"max": 0.07593662648115937,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25545666867230254,
"min": 0.25162059078623616,
"max": 0.3542701066540116,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20553171203709114,
"min": 0.12332784381635743,
"max": 0.2954108135811254,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8221268481483646,
"min": 0.49331137526542973,
"max": 1.4330853115694195,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.681818181818183,
"min": 3.6136363636363638,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 159.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.6136363636363638,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 159.0,
"max": 1401.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1763984573",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1763985047"
},
"total": 474.002748976,
"count": 1,
"self": 0.7508505089999744,
"children": {
"run_training.setup": {
"total": 0.03444765700010066,
"count": 1,
"self": 0.03444765700010066
},
"TrainerController.start_learning": {
"total": 473.21745080999995,
"count": 1,
"self": 0.4632499570291202,
"children": {
"TrainerController._reset_env": {
"total": 2.771038189000137,
"count": 1,
"self": 2.771038189000137
},
"TrainerController.advance": {
"total": 469.85276500197097,
"count": 18192,
"self": 0.4701045859892474,
"children": {
"env_step": {
"total": 347.5795274629902,
"count": 18192,
"self": 272.59963268898923,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.70332076100749,
"count": 18192,
"self": 1.4031430370005182,
"children": {
"TorchPolicy.evaluate": {
"total": 73.30017772400697,
"count": 18192,
"self": 73.30017772400697
}
}
},
"workers": {
"total": 0.2765740129934784,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.3319914920153,
"count": 18192,
"is_parallel": true,
"self": 233.35684124497948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005433545999949274,
"count": 1,
"is_parallel": true,
"self": 0.004049643999678665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013839020002706093,
"count": 10,
"is_parallel": true,
"self": 0.0013839020002706093
}
}
},
"UnityEnvironment.step": {
"total": 0.037928327999907196,
"count": 1,
"is_parallel": true,
"self": 0.0006087799995384557,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000671953000164649,
"count": 1,
"is_parallel": true,
"self": 0.000671953000164649
},
"communicator.exchange": {
"total": 0.03465854000000945,
"count": 1,
"is_parallel": true,
"self": 0.03465854000000945
},
"steps_from_proto": {
"total": 0.0019890550001946394,
"count": 1,
"is_parallel": true,
"self": 0.0004014749999896594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00158758000020498,
"count": 10,
"is_parallel": true,
"self": 0.00158758000020498
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.9751502470358,
"count": 18191,
"is_parallel": true,
"self": 10.932392412078116,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.764588957004662,
"count": 18191,
"is_parallel": true,
"self": 5.764588957004662
},
"communicator.exchange": {
"total": 182.35263773796646,
"count": 18191,
"is_parallel": true,
"self": 182.35263773796646
},
"steps_from_proto": {
"total": 38.92553113998656,
"count": 18191,
"is_parallel": true,
"self": 6.964440051011934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.961091088974626,
"count": 181910,
"is_parallel": true,
"self": 31.961091088974626
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.80313295299152,
"count": 18192,
"self": 0.6110367460189536,
"children": {
"process_trajectory": {
"total": 27.346002725972312,
"count": 18192,
"self": 26.677707346972284,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6682953790000283,
"count": 4,
"self": 0.6682953790000283
}
}
},
"_update_policy": {
"total": 93.84609348100025,
"count": 90,
"self": 38.664843354015375,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.18125012698488,
"count": 4587,
"self": 55.18125012698488
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1069996617152356e-06,
"count": 1,
"self": 1.1069996617152356e-06
},
"TrainerController._save_models": {
"total": 0.1303965550000612,
"count": 1,
"self": 0.0008819559998300974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1295145990002311,
"count": 1,
"self": 0.1295145990002311
}
}
}
}
}
}
}